Finite-Data Performance Guarantees for the Output-Feedback Control of an Unknown System

03/25/2018
by   Ross Boczar, et al.
0

As the systems we control become more complex, first-principle modeling becomes either impossible or intractable, motivating the use of machine learning techniques for the control of systems with continuous action spaces. As impressive as the empirical success of these methods have been, strong theoretical guarantees of performance, safety, or robustness are few and far between. This paper takes a step towards such providing such guarantees by establishing finite-data performance guarantees for the robust output-feedback control of an unknown FIR SISO system. In particular, we introduce the "Coarse-ID control" pipeline, which is composed of a system identification step followed by a robust controller synthesis procedure, and analyze its end-to-end performance, providing quantitative bounds on the performance degradation suffered due to model uncertainty as a function of the number of experiments run to identify the system. We conclude with numerical examples demonstrating the effectiveness of our method.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/10/2022

Robust Data-Driven Output Feedback Control via Bootstrapped Multiplicative Noise

We propose a robust data-driven output feedback control algorithm that e...
research
03/02/2021

Reachability-based Identification, Analysis, and Control Synthesis of Robot Systems

We introduce reachability analysis for the formal examination of robots....
research
05/07/2021

Learning-enhanced robust controller synthesis with rigorous statistical and control-theoretic guarantees

The combination of machine learning with control offers many opportuniti...
research
09/26/2018

Safely Learning to Control the Constrained Linear Quadratic Regulator

We study the constrained linear quadratic regulator with unknown dynamic...
research
10/04/2017

On the Sample Complexity of the Linear Quadratic Regulator

This paper addresses the optimal control problem known as the Linear Qua...
research
05/06/2021

Practical and Rigorous Uncertainty Bounds for Gaussian Process Regression

Gaussian Process Regression is a popular nonparametric regression method...
research
02/02/2019

Transparent Concurrency Control: Decoupling Concurrency Control from DBMS

For performance reasons, conventional DBMSes adopt monolithic architectu...

Please sign up or login with your details

Forgot password? Click here to reset